A Survey on Retrieval-Augmented Text Generation

TL;DR

This survey reviews retrieval-augmented text generation, highlighting its paradigm, notable approaches across various NLP tasks, and future research directions, emphasizing its advantages over traditional models and recent state-of-the-art performance.

Contribution

It provides a comprehensive overview of retrieval-augmented text generation methods, categorizes approaches by task, and discusses future research directions in the field.

Findings

Retrieval-augmented models outperform traditional generation models in several NLP tasks.

The survey categorizes approaches based on task types like dialogue and translation.

Future directions include improving retrieval methods and integration techniques.

Abstract

Recently, retrieval-augmented text generation attracted increasing attention of the computational linguistics community. Compared with conventional generation models, retrieval-augmented text generation has remarkable advantages and particularly has achieved state-of-the-art performance in many NLP tasks. This paper aims to conduct a survey about retrieval-augmented text generation. It firstly highlights the generic paradigm of retrieval-augmented generation, and then it reviews notable approaches according to different tasks including dialogue response generation, machine translation, and other generation tasks. Finally, it points out some important directions on top of recent methods to facilitate future research.